EP3936824A1 - Verfahren zur charakterisierung einer von einem nutzer zurückgelegten strecke - Google Patents

Verfahren zur charakterisierung einer von einem nutzer zurückgelegten strecke Download PDF

Info

Publication number
EP3936824A1
EP3936824A1 EP21179443.3A EP21179443A EP3936824A1 EP 3936824 A1 EP3936824 A1 EP 3936824A1 EP 21179443 A EP21179443 A EP 21179443A EP 3936824 A1 EP3936824 A1 EP 3936824A1
Authority
EP
European Patent Office
Prior art keywords
path
distance
characterization
previous
fréchet
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
EP21179443.3A
Other languages
English (en)
French (fr)
Inventor
Francisco Jose GONZALEZ DE COSSIO ECHEVERRIA
Guillaume SABIRON
Laurent Thibault
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
IFP Energies Nouvelles IFPEN
Original Assignee
IFP Energies Nouvelles IFPEN
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by IFP Energies Nouvelles IFPEN filed Critical IFP Energies Nouvelles IFPEN
Publication of EP3936824A1 publication Critical patent/EP3936824A1/de
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
    • G01C21/34—Route searching; Route guidance
    • G01C21/3407—Route searching; Route guidance specially adapted for specific applications
    • G01C21/3423—Multimodal routing, i.e. combining two or more modes of transportation, where the modes can be any of, e.g. driving, walking, cycling, public transport
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
    • G01C21/28—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network with correlation of data from several navigational instruments
    • G01C21/30—Map- or contour-matching
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
    • G01C21/34—Route searching; Route guidance
    • G01C21/3446—Details of route searching algorithms, e.g. Dijkstra, A*, arc-flags, using precalculated routes
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
    • G01C21/34—Route searching; Route guidance
    • G01C21/3453—Special cost functions, i.e. other than distance or default speed limit of road segments
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/29—Geographical information databases

Definitions

  • the present invention relates to the field of the characterization of a path traveled by a user, in particular the characterization of the membership of the path traveled with a grouping (group, or in English "cluster") of previous paths, and/or of the characterization of the mode of transport of the user.
  • the field of transport is an essential aspect of daily life on which the global economy depends heavily. However, it also plays a major role in degrading air quality and increasing CO 2 emissions, especially in urban areas. According to the World Health Organization (WHO), transport is one of the main sources of air pollution, and it is directly linked to multiple respiratory and cardiovascular diseases. In addition, the global transport is responsible for about 24% of direct CO 2 emissions from combustion of fuels, including nearly three quarters correspond to cars, trucks, buses and motorcycles, which exacerbates the phenomenon of global warming. Other types of harmful emissions include nitrogen oxides (NOx), ground-level ozone (O 3 ) and particulate matter (PM), which generally exceed recommended limits.
  • NOx nitrogen oxides
  • O 3 ground-level ozone
  • PM particulate matter
  • the technological development of portable devices and wireless communication has accelerated in recent years, in particular thanks to geolocation systems (for example GPS from the English "Global Positioning System”), by means of a smart phone, etc. It is thus possible to extract all types of information concerning the movements of users around the world: the mode of transport used is particularly valuable information.
  • geolocation systems for example GPS from the English "Global Positioning System”
  • a first approach to identify the mode of transport can consist of an approach based on speed. It should be noted that such a speed-based approach has serious flaws since it ignores common phenomena such as traffic or weather conditions. There is, therefore, a need for identification of the mode of transport using the datasets available from mobile devices equipped with geolocation systems.
  • a natural first step towards this objective of identifying the mode of transport consists in reducing the magnitude of the data by grouping the trajectories into representative groupings (groups, or in English “clusters”) presenting similar characteristics. Each group can have one representative for whom transportation is readily available.
  • trajectory clustering strategy requires a carefully chosen method to measure the similarity between two given trajectories; raw GPS data tends to be asynchronous, undersampled, and with varying sample rates.
  • the grouping of geographical trajectories based on a measure of full or partial similarity can be used for a wide range of applications, for example: knowledge of user trends, mobility forecasting, traffic control and optimal trip planning. .
  • the clustering method can be interpreted as a data reduction technique in order to summarize the user's travel activity over a long period and with a high spatio-temporal resolution.
  • the so-called Fréchet distance offers an effective compromise between generality and specificity. Indeed, it is invariant with respect to the velocity of the trajectory, but strongly depends on the continuous flow of the trajectory.
  • the Fréchet distance between path A and B can be informally described as the shortest leash length allowing a person on path A to walk a dog on path B (without backing up).
  • the measure of dynamic temporal distortion (DTW), introduced in the field of speech recognition as a measure of similarity between time series, is also relevant.
  • the Fréchet distance is given by the formula: where A and B are curves on a metric space (distance d), and where ⁇ and ⁇ represent different parametrizations of curves.
  • the Fréchet distance is sensitive to outliers.
  • Another limitation of the original Fréchet distance is the identification of portions of similar trajectories.
  • the Fréchet distance was used in particular in the method described in the patent application US2015/0354973 , with the aim of placing measurement signals on a road map (“map matching”).
  • said characterization concerns the classification of said path to be characterized in a representative grouping of paths.
  • said characterization concerns the determination of at least one mode of transport of said user for said path to be characterized.
  • said path to be characterized is segmented into at least two sub-paths, and said at least one mode of transport of said user is determined for each sub-path.
  • said at least one mode of transport is determined by comparison with a multimodal travel planning tool.
  • said multimodal planning tool includes travel mapping and public transport data.
  • At least one complementary parameter of said path to be characterized is measured, said complementary parameter being chosen from among the speed of said user, the acceleration of said user, the accuracy of said geolocation sensor, the altitude of said user, and implements an additional criterion to characterize said path to be characterized as a function of said additional parameter.
  • said modified discrete Fréchet distance is determined by limiting, in said optimal sequencing of pairs of points, the number of links for a single point of a path, preferably the limit number of links is between 3 and 10 , preferably between 4 and 7.
  • said modified discrete Fréchet distance is determined after elimination of the maximum values of the distance in said optimal sequencing of pairs of points.
  • the method further comprises a step of pre-processing the measurements by spatial distance interpolation.
  • said database of said previous journeys comprises only previous journeys of said user, with at least the geolocation and timestamp data of said previous journeys.
  • said database includes information related to the mode of transport for at least one previous journey.
  • said database includes at least one representative grouping of said previous journeys.
  • the invention relates to a computer program product downloadable from a communication network and/or recorded on a computer-readable medium and/or executable by a processor or a server, comprising program code instructions for implementation of the method according to one of the preceding characteristics, when said program is executed on a computer or on a mobile telephone.
  • the present invention relates to a method for characterizing a path traveled by a user.
  • the term traveled by a user is a journey made by a user between an origin and a destination with any means of transport (vehicle, bicycle, public transport: bus, tram, train, metro, walking, etc.).
  • vehicle, bicycle, public transport bus, tram, train, metro, walking, etc.
  • the user can use several different means of transport, this is called a multimodal journey (for example a combination of public transport, or a combination of public transport and travel on foot, or by bicycle, etc. .).
  • the path traveled by the user is called the path to be characterized.
  • the characterization concerns the determination of at least one characteristic representative of the path.
  • the characterization may concern the determination of the mode(s) of transport (that is to say the means(s) of locomotion).
  • the characterization may relate to the belonging of the path to be characterized to a representative grouping of paths (to a “cluster”), the paths belonging to the same representative grouping of paths having similar attributes, in particular similar paths.
  • the characterization method uses a database comprising data from previous journeys.
  • the previous paths are paths traveled prior to the path to be characterized, and for which data is available: in particular the location, the timestamp.
  • the database may further comprise other data relating to previous journeys, for example, the mode of transport, the speed of the user, the altitude of the user, etc.
  • the database may be stored on computer memory.
  • the database can comprise only data from previous journeys of the user of the journey to be characterized.
  • the characterization of the path can be representative of the habits of the user.
  • the database may include data from past journeys of multiple users.
  • the database can comprise a large number of previous journeys, which allows better precision in the characterization of the journey to be characterized.
  • determining discrete modified Fréchet distances and of characterization can be implemented by a computer system.
  • a computer system can comprise a computer storage memory, a calculation processor, and communication means, in particular with the measurement means.
  • a BDD database includes data from past journeys. During the path to be characterized, the position and the timestamp are measured MES. These measurements, and the data from the database BDD are then used to determine a modified discrete Fréchet distance DFM between the path to be characterized and the previous paths. This modified discrete Fréchet distance DFM then makes it possible to determine the characterization CAR of the path to be characterized.
  • the method may comprise an additional step of pre-processing the measurements before the step of determining modified Fréchet distances. This step of pre-processing the measurements makes it possible to improve the measurement sampling.
  • a computer system can comprise a computer storage memory, a calculation processor, and communication means, in particular with the measurement means.
  • a BDD database includes data from past journeys. During the path to be characterized, the position and the timestamp are measured MES. An INT preprocessing of the MES measurements is carried out. These preprocessed measurements, and the data from the database BDD are then used to determine a discrete modified Fréchet distance DFM between the path to be characterized and the previous paths. This discrete modified Fréchet distance DFM then makes it possible to determine the characterization CAR of the path to be characterized.
  • the database may comprise at least one representative grouping of routes (“cluster”).
  • cluster the modified Fréchet distance can be determined for a single previous journey of each representative group of journeys, preferably a previous journey for which the mode of transport is known.
  • the number of modified Fréchet distances determined is limited, which reduces the calculation time.
  • a database BDD includes data from previous journeys, and groupings representative of previous journeys GPR.
  • the position and the timestamp are measured MES.
  • These measurements, and the data from the BDD database, and the representative GPR clusters are then used to determine a discrete modified Fréchet distance DFM between the path to be characterized and the previous paths of each representative GPR cluster. This discrete modified Fréchet distance DFM then makes it possible to determine the characterization CAR of the path to be characterized.
  • the position and timestamp of a plurality of points of the path to be characterized are measured by means of a geolocation sensor.
  • the geolocation sensor can be a satellite positioning sensor, such as the GPS system (Global Positioning System), the Galileo system, etc.
  • the geolocation sensor can be on board the vehicle or deported (for example by means of a smart telephone, English “smartphone”).
  • the geolocation sensor can be deported in a smart phone, so as to be suitable for any type of mode of transport.
  • the timestamp can be used in particular for preprocessing (see next step).
  • the interpolation can also be carried out with a virtual timestamp.
  • this step is optional, and corresponds to the second embodiment of the invention illustrated in picture 2 .
  • a preprocessing of the measurements is implemented, preferably by means of a spatial interpolation in distance (in other words by imposing a minimum distance between two consecutive measurement points), in order to improve the measurement sampling.
  • the first step makes it possible to know the geolocation of a plurality of measurement points.
  • the measurement of the journey to be characterized may include several measurement points more or less distant, while they theoretically correspond to the same physical point of the path travelled. This disparity of the measurement points can generate a less consistent determination of the averaged Fréchet distances, which can generate a less precise characterization of the path to be characterized.
  • this pre-processing makes it possible to sample the data in order to have a point every 50m (or 25m, 100m, 150m, etc.).
  • the GPS-type geolocation sensor can perform the measurement at a frequency of 1Hz so when the user stops for example at a red light, there are many points in the same place, which can increase the distance de Fréchet without having to travel.
  • a distance is determined between the path to be characterized and the previous path by means of the modified discrete Fréchet distance.
  • the "classic" Fréchet distance between trajectory A and B can be informally described as the length of the shortest leash allowing a person on path A to walk a dog on path B (without reverse).
  • the modified discrete Fréchet distance a determination of a distance based on the method implemented for the calculation of the "classic" Fréchet distance, but by not calculating the greatest distance between the points of the two paths considered. , but an average of the distances between the two paths considered in a discrete way. This discrete modified Fréchet distance makes it possible to overcome certain aberrant measurements.
  • the step of determining the links that connect a point of each polyline is performed dynamically and recursively. Two discrete paths X and Y of respective lengths N and M are considered here.
  • x n corresponds to the nth element of path X and y m the mth element of path Y, and d the distance between the nth element of path X and the mth element of path Y.
  • a modification that can be made by the invention may consist in saturating the number of links per point, namely, if x k (or y l ) appears more than sat times in the sequence P (and respectively in the sequence d *), we removes the P i which contain x k (or y l ) and we then obtain a sequencing P s ⁇ t (and respectively in a sequence d Sat * ).
  • sat is a limit value preferably chosen around 5. This distance is called “saturated discrete modified Fréchet distance”.
  • the modified discrete Fréchet distance is obtained by taking the average of the distance sequence d* or d Sat * .
  • the discrete modified Fréchet distance can be obtained by taking the truncated mean of the distance sequence.
  • the truncated mean of a vector is a measure of arithmetic mean by eliminating extreme values.
  • the truncated mean can eliminate only the largest values. This distance is called “truncated discrete modified Fréchet distance”.
  • the figure 5 illustrates, schematically and in a non-limiting manner, the determination of the discrete modified Fréchet distance according to one embodiment of the invention.
  • a path A represented by polyline A and a path B represented by polyline B.
  • Paths A and B are traveled in the direction of the arrows indicated.
  • This figure shows the connections L between each path A and B (which could correspond to a leash between the walker on path A and his dog on path B).
  • the links L have a variable distance d.
  • each point of a path can be linked to several points of the other path. For example, point P of path A is connected to a plurality of points Q 1 , ..., Q n of path B.
  • the discrete modified Fréchet distance can be determined by limiting the number of links for a single point of a path, preferably the limit number of links is between 3 and 10, preferably between 4 and 7, and can be equal to 5.
  • the number of links starting from each point is limited.
  • the path to be characterized is characterized by a comparison of the modified discrete Fréchet distances determined in the previous step between the at least two previous paths of said database and the path to be characterized.
  • the threshold can be approximately 200m.
  • the path to be characterized can be assigned the characterization of the previous path which minimizes the discrete modified Fréchet distance.
  • the two criteria can be combined: the minimum value can be compared with a threshold, and the path to be characterized can be characterized if the minimum value is less than the threshold.
  • the additional parameter being able to be chosen from among the speed of the user, the acceleration of the user, the precision of the sensor of geolocation, the altitude of the user, and an additional criterion can be implemented to characterize the path to be characterized as a function of the complementary parameter.
  • the reduced discrete modified Fréchet distance i.e. minimum and/or less than a threshold
  • the speed of movement of the user it is possible to differentiate the mode of transport and/or the representative grouping of journeys.
  • this step can also include the recording of the path traveled and characterized in the database of previous paths.
  • the path traveled and characterized then becomes a previous path for the reiteration of the method for another path traveled by the user.
  • the database is completed with each use, which promotes the reliability of the characterization.
  • the characterization may relate to the membership of the path to be characterized in a representative grouping of paths (“cluster”).
  • the path to be characterized can be assigned the same representative grouping of paths as that of the previous path in the database (embodiment of the picture 3 ) for which the discrete modified Fréchet distance is reduced (that is to say minimal and/or less than a threshold).
  • the characterization may relate to the detection of the mode of transport of the route to be taken.
  • the path to be characterized can be segmented into sub-paths, and a transport mode can be assigned to each sub-path.
  • a first implementation of this variant may consist in allocating the mode of transport of the previous journey for which the discrete modified Fréchet distance is reduced (that is to say minimum and/or lower than a threshold).
  • This implementation requires that at least one previous journey of the database includes data relating to the mode of transport of this previous journey.
  • a second implementation of this variant may consist in comparing the path to be characterized with at least one path obtained with a multimodal travel planning tool.
  • This tool provides transportation analysis and multimodal trip planning services.
  • This multimodal planning tool can include travel mapping and public transport data.
  • a route obtained by this tool can be segmented in such a way that the specific mode of transport is well defined for each portion of the route.
  • the comparison of the path to be characterized with at least one path obtained with a multimodal travel planning tool can be carried out by means of the discrete modified Fréchet distance implemented in the previous step.
  • the route to be characterized is then assigned the means of transport corresponding to the route obtained by this multimodal trip planning tool having a reduced discrete modified Fréchet distance (minimum value and/or lower than a threshold).
  • the multimodal travel planning tool may be available as an online service (“webservice”).
  • the computer means implemented by the method according to the invention may comprise means of connection to the online service, in particular an Internet connection.
  • a BDD database includes data from past journeys. During the path to be characterized, the position and the timestamp are measured MES. These measurements, and data from the BDD database are then used to determine a discrete modified Fréchet distance DFM between the path to characterize and previous journeys. In addition, a discrete modified Fréchet distance DFM is determined between the path to be characterized and a path obtained from a multimodal path planning tool OTP. These modified Fréchet distances DFM then make it possible to determine the characterization CAR of the path to be characterized, in this case the mode of transport mdt.
  • the characterization may relate to the detection of the mode of transport of the route to be traversed and the membership of the route to be characterized in a representative grouping of routes.
  • the first variant can be combined with one of the implementations of the second variant described above. For example, it is possible initially to determine the membership of the path to be characterized in a representative grouping of paths. Then, the mode of transport corresponding to the representative grouping of journeys is assigned to the route to be characterized. This exemplary embodiment imposes that each representative grouping of journeys comprises at least one previous journey for which a mode of transport is identified.
  • the characterization method may include a step of constructing representative groupings (“clusters”) of paths from the database.
  • this step of constructing representative groupings (“clusters”) can be implemented by applying the discrete modified Fréchet distance by comparing the previous paths in the database in pairs.
  • the method may include an optional step of displaying the characterization of the route travelled.
  • the characterization can be displayed on a road map.
  • This display can take the form of a note or a color code (for example, one color per mode of transport and/or one color per “cluster”).
  • This display can be produced on board a vehicle: on an autonomous portable device, such as a geolocation device (of the GPS type), a portable telephone (of the smart telephone type). It is also possible to display the characterization of the path to be characterized on a website.
  • the invention also relates to a computer program product downloadable from a communication network and/or recorded on a computer-readable medium and/or executable by a processor or a server.
  • This program comprises program code instructions for implementing the method as described above, when the program is executed on a computer or a mobile telephone or any similar system.
  • paths measured by a geolocation sensor within a smart telephone are characterized.
  • the measured and previous journeys are located in the Lyon metropolitan area.
  • the figure 6 and 7 represent two maps of the Lyon metropolitan area. For the sake of readability of the maps, the roads are not represented.
  • the figure 6 illustrates the path to be characterized T and the first prior path T1, as well as several L links between the points of the first path to be characterized T and the first prior path T1 are represented (all of these links are not represented).
  • the map of the figure 7 illustrates the path to be characterized T and the second prior path T2, as well as several L links between the points of the first path to be characterized T and the second prior path T2 are shown (all of these links are not shown).
  • the path to be characterized T is similar to the previous path T2, in fact, the path to be characterized T is partly superimposed on the previous path T2.
  • the discrete modified Fréchet distance is determined according to the method according to the invention.
  • the discrete modified Fréchet distance is 2241 m
  • the discrete modified Fréchet distance is 41 m.
  • the second example corresponds to the embodiment of the figure 4 : determining the mode of transport using a multimodal travel planning tool.
  • different routes are determined using the multimodal trip planning tool.
  • the figure 8 represents a map of the Lyon metropolitan area. For the sake of readability of the maps, the roads are not represented.
  • the figure 8 illustrates the route T traveled represented by crosses and the different routes T3, T4, T5, T6 obtained by the multimodal trip planning tool. In this case, the route to be characterized appears as a sub-route of a set of routes obtained by the multimodal trip planning tool.
  • the modified Fréchet distance of path T3 is 129.58m, that of path T4 is 130.53 m, that of path T5 is 18.61m, and that of path T6 is 19.75 m.
  • the path can be assigned the transport mode of the path T5, which minimizes the discrete modified Fréchet distance. Thanks to this, it can be determined that the route traveled was made by means of the Lyon tramway T1, which corresponds well to what was entered by the user.
  • the method according to the invention makes it possible to robustly characterize a path traveled by a user, by means of measurements by a geolocation sensor.

Landscapes

  • Engineering & Computer Science (AREA)
  • Remote Sensing (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Automation & Control Theory (AREA)
  • Databases & Information Systems (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • General Engineering & Computer Science (AREA)
  • Navigation (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Injection Moulding Of Plastics Or The Like (AREA)
EP21179443.3A 2020-07-08 2021-06-15 Verfahren zur charakterisierung einer von einem nutzer zurückgelegten strecke Pending EP3936824A1 (de)

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
FR2007213A FR3112398B1 (fr) 2020-07-08 2020-07-08 Procédé de caractérisation d’un trajet parcouru par un utilisateur

Publications (1)

Publication Number Publication Date
EP3936824A1 true EP3936824A1 (de) 2022-01-12

Family

ID=72801683

Family Applications (1)

Application Number Title Priority Date Filing Date
EP21179443.3A Pending EP3936824A1 (de) 2020-07-08 2021-06-15 Verfahren zur charakterisierung einer von einem nutzer zurückgelegten strecke

Country Status (3)

Country Link
US (1) US20220011123A1 (de)
EP (1) EP3936824A1 (de)
FR (1) FR3112398B1 (de)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
FR3132570A1 (fr) * 2022-02-09 2023-08-11 IFP Energies Nouvelles Procédé de détermination d’au moins une route entre une zone géographique d’origine et une zone géographique de destination

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11345342B2 (en) * 2019-09-27 2022-05-31 Intel Corporation Potential collision warning system based on road user intent prediction
FR3142643A1 (fr) 2022-11-28 2024-05-31 IFP Energies Nouvelles Procédé de détermination d’un mode de transport d’un trajet parcouru par au moins un utilisateur

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20150354973A1 (en) 2013-03-15 2015-12-10 Hewlett-Packard Development Company, L.P. Map matching

Family Cites Families (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20160362118A1 (en) * 2011-08-31 2016-12-15 Pulsar Informatics, Inc. Driver performance metric
US8755967B1 (en) * 2012-03-23 2014-06-17 Google Inc. Estimating road lane geometry using lane marker observations
US10427676B2 (en) * 2017-05-31 2019-10-01 GM Global Technology Operations LLC Trajectory planner for autonomous driving using bézier curves
GB201414778D0 (en) * 2014-08-20 2014-10-01 Jaguar Land Rover Ltd Route planning device and method
US10228259B2 (en) * 2016-03-21 2019-03-12 Ford Global Technologies, Llc. Systems, methods, and devices for communicating drive history path attributes
US20190186939A1 (en) * 2017-12-20 2019-06-20 Nio Usa, Inc. Intelligent trip prediction in autonomous vehicles
US11187542B2 (en) * 2019-02-26 2021-11-30 Here Global B.V. Trajectory time reversal
US11099020B2 (en) * 2019-05-28 2021-08-24 Here Global B.V. Method and apparatus for optimizing intermodal route computations
US11875678B2 (en) * 2019-07-19 2024-01-16 Zoox, Inc. Unstructured vehicle path planner

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20150354973A1 (en) 2013-03-15 2015-12-10 Hewlett-Packard Development Company, L.P. Map matching

Non-Patent Citations (7)

* Cited by examiner, † Cited by third party
Title
BESSE PHILIPPE C ET AL: "Review and Perspective for Distance-Based Clustering of Vehicle Trajectories", IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, IEEE, PISCATAWAY, NJ, USA, vol. 17, no. 11, 1 November 2016 (2016-11-01), pages 3306 - 3317, XP011627030, ISSN: 1524-9050, [retrieved on 20161028], DOI: 10.1109/TITS.2016.2547641 *
F. ASGARIA. SULTANH. XIONGV. GAUTHIERM.A. EI-YACOUBI: "Ct-mapper: mapping sparse multimodal cellular trajectories using a multilayer transportation network", COMPUT. COMMUN., vol. 95, 2016, pages 69 - 81
F. ASGARIA. SULTANH. XIONGV. GAUTHIERM.A. EL-YACOUBI: "Ct-mapper: mapping sparse multimodal cellular trajectories using a multilayer transportation network", COMPUT. COMMUN., vol. 95, 2016, pages 69 - 81, XP055297966 *
JOHN DOYLE ET AL: "Utilising Mobile Phone Billing Records for Travel Mode Discovery", ISSC, 1 January 2011 (2011-01-01), XP055297821 *
P.C. BESSEB. GUILLOUETJ.-M. LOUBESF. ROYER: "Review and Perspective for Distance-based Clustering of Vehicle Trajectories", IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, vol. 17, no. 11, 2016, pages 3306 - 3317, XP011627030, DOI: 10.1109/TITS.2016.2547641
S. ATEVG. MILLERN.P. PAPANIKOLOPOULOS: "Clustering of Vehicle Trajectories", IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, vol. 11, no. 3, 2010, pages 647 - 657
ZBIGNIEW SMOREDA ET AL: "Spatiotemporal data from mobile phones for personal mobility assessment", 1 January 2013 (2013-01-01), XP055297817, Retrieved from the Internet <URL:http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.649.8361&rep=rep1&type=pdf> [retrieved on 20210326], DOI: 10.1108/9781781902882-041 *

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
FR3132570A1 (fr) * 2022-02-09 2023-08-11 IFP Energies Nouvelles Procédé de détermination d’au moins une route entre une zone géographique d’origine et une zone géographique de destination
EP4239289A1 (de) * 2022-02-09 2023-09-06 IFP Energies nouvelles Verfahren zur bestimmung mindestens einer route zwischen einem geographischen gebiet der herkunft und einem geografischen zielbereich

Also Published As

Publication number Publication date
US20220011123A1 (en) 2022-01-13
FR3112398A1 (fr) 2022-01-14
FR3112398B1 (fr) 2022-10-14

Similar Documents

Publication Publication Date Title
EP3936824A1 (de) Verfahren zur charakterisierung einer von einem nutzer zurückgelegten strecke
Newson et al. Hidden Markov map matching through noise and sparseness
US7706964B2 (en) Inferring road speeds for context-sensitive routing
JP2020057423A (ja) オン・デマンドサービスの情報を提供する方法及びシステム
US20180087922A1 (en) Discovering points of entry to a location
US8554473B2 (en) Energy efficient routing using an impedance factor
EP3462404A1 (de) Verfahren zur bestimmung der indikatoren für die verschmutzung durch verkehrsmittel unter berücksichtigung der tatsächlichen benutzung
US20230066501A1 (en) Method, apparatus, and system for traffic estimation based on anomaly detection
US11042648B2 (en) Quantification of privacy risk in location trajectories
Romanillos et al. Cyclists do better. Analyzing urban cycling operating speeds and accessibility
JP7399891B2 (ja) ナビゲーション中に難しい操縦についての追加の命令を提供すること
EP4075408A1 (de) Verfahren zur bestimmung der menge der von einem fahrzeug auf einem strassenabschnitt ausgestossenen schadstoffemissionen
WO2020239503A1 (fr) Procede de prediction d&#39;au moins un profil de la vitesse d&#39;un vehicule sur un reseau routier
EP3760506A1 (de) Verfahren zur charakterisierung des zustands einer fahrbahn
US20220100796A1 (en) Method, apparatus, and system for mapping conversation and audio data to locations
US20240328803A1 (en) Methods and Systems for Determining Estimated Travel Times Through a Navigable Network
EP2861937A1 (de) Verfahren zur schätzung einer reisezeit eines fahrzeugs auf einem strassennetz
EP3653992B1 (de) Verfahren zur bestimmung einer kumulierung von schlechten witterungsbedingungen auf einer strecke
JP4839409B2 (ja) 旅行時間予測システムおよび旅行時間予測プログラムならびにナビゲーションシステム
EP3996064B1 (de) Verfahren zur bestimmung einer anzahl von fahrzeugdurchfahrten auf mindestens einem strassenabschnitt eines strassennetzes
EP4375619A2 (de) Verfahren zur bestimmung eines transportmodus eines von mindestens einem benutzer durchströmten weges
FR3088113A1 (fr) Procede de prediction du prochain trajet d’une personne
EP4181100A1 (de) Verfahren zur bestimmung eines maximalen durchsatzes und/oder eines logistischen durchflusses von fahrzeugen auf einem strassennetz
FR3090148A1 (fr) Procédé de recalage cartographique multimodal basé sur le comportement répétitif humain
EP4239289A1 (de) Verfahren zur bestimmung mindestens einer route zwischen einem geographischen gebiet der herkunft und einem geografischen zielbereich

Legal Events

Date Code Title Description
PUAI Public reference made under article 153(3) epc to a published international application that has entered the european phase

Free format text: ORIGINAL CODE: 0009012

STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: THE APPLICATION HAS BEEN PUBLISHED

AK Designated contracting states

Kind code of ref document: A1

Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR

B565 Issuance of search results under rule 164(2) epc

Effective date: 20211105

STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: REQUEST FOR EXAMINATION WAS MADE

17P Request for examination filed

Effective date: 20220712

RBV Designated contracting states (corrected)

Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR

STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: EXAMINATION IS IN PROGRESS

17Q First examination report despatched

Effective date: 20240103